"Context compression techniques and methods" matching MCP servers:

Compression AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Enables AI agents and MCP clients to compress retrieved web documents against a query, pruning irrelevant noise through deterministic algorithmic scoring so downstream context stays lean. It exposes this capability over the Model Context Protocol for integration with Claude Desktop, Cursor, and similar clients.

Aggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.

Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

Sovereign, deterministic, local-first context and DAG lifecycle engine with native stdio MCP server for autonomous AI coding agents.

Read-only repository context explorer for coding agents. Provides repository exploration tools via CLI or MCP adapter.

Compresses multi-turn conversation history by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities, deterministically cutting inference costs by 40-60%. Runs as a zero-dependency Python MCP server or importable module, compatible with Claude Desktop, Cursor, and other MCP runtimes.

Enables AI agents to search, filter, and monitor curated AI model API free credits and low-cost token promotions through eight tools, four resources, and three prompts — including finding deals expiring soon, checking eligibility and blocked conditions, and producing daily briefs.

MCP server that validates AI-generated 1C:Enterprise (BSL) code against the real platform API. Catches unknown enum values, wrong argument counts, and missing type members by parsing the platform syntax-helper (shcntx_ru.hbk) — independent Rust implementation with built-in expression validator.

An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.

Fantasy Premier League stats and press coverage for AI agents: read-only SQL over FPL player, fixture and gameweek data, plus semantic search over BBC Sport and Guardian articles and FPL injury news. Bring your own PostgreSQL and Pinecone, with bundled ingestion jobs.

MCP server providing lossless file reads with deduplication, per-repo token metering, and HMAC-signed context receipts. Enables auditable, vendor-neutral measurement of what an AI agent saw.

Provides an external context buffer so a local model can maintain session memory across long tasks and search and page through large documents without loading them whole into its limited context window.

Enables AI coding agents to reduce token usage by condensing source code into AST skeletons, extracting specific symbols, compressing logs, and estimating token budgets.

MCP server that inspects local codebases and generates source-grounded context packs for coding agents, with tools for repository search, symbols, dependencies, Git analysis, and context generation.

Exposes tools for AI assistants to query a persistent SQLite+FTS5 index of C/C++ symbols parsed from real build commands, enabling sub-millisecond lookup, full-text search, and natural-language explanation without hallucination.

Persistent project context (AGENTS.md), cross-session memory, and identity — discoverable by any MCP client.

Provides redacted access to a private local knowledgebase for coding agents, allowing them to inspect files while hiding sensitive names and identifiers.